Audexum

by com.audexum

Overview Discussions Admin

Server Details

Text to speech and transcription for any AI model: MP3 voiceovers, audio and YouTube to text.

Ownership verified

Status: Healthy
Uptime: 100.0% over the last 24 hours
OAuth: Works in Glama
Last Tested: 2026-11-13 23:37
Transport: Streamable HTTP · MCP 2025-11-25
URL
ChatGPT: –
Claude: –

TDQS

A4.2/5.0

Scored 2026-10-23 18:20 across 7 tools

Disambiguation4/5

Each tool targets a distinct action (account lookup, guide, generation, upgrade link, voice listing, file transcription, YouTube captions), and descriptions explicitly route the agent away from the closest confusions (transcribe vs youtube_transcript, audexum_guide vs account_status). The only residual overlap is between account_status's pricing_url, get_upgrade_link, and audexum_guide's pricing content, which takes a careful read to separate.

Naming Consistency4/5

All names are consistently snake_case, which is the main thing that matters. There is minor variation in shape: verb_noun (generate_speech, get_upgrade_link, list_voices), noun_phrase (account_status, audexum_guide, youtube_transcript), and a bare verb (transcribe).

Tool Count5/5

Seven tools is well within the sweet spot and every one earns its place: two read-only reference tools, one account check, two generation/transcription actions, and two link/voice helpers. Nothing feels padded or missing at this scope.

Completeness4/5

Core lifecycle for a speech API is covered: discover voices, generate, transcribe, check credits, upgrade. Gaps are minor but real — no tool for the other products the guide advertises (dubbing, audiobooks, voice cloning), no job status or result retrieval beyond the returned MP3 link, and no way to preview cost before a call.

Publisher details

Operator: Audexum
Operator website: https://audexum.com
Vendor relationship: First-party
Documentation: https://audexum.com/integrations/mcp
Trust center: Not available
Restrictions: Requires a free Audexum account (OAuth sign-in). The free plan includes monthly credits; the v4 voice engine needs the Creator plan or a credit pack.

Available Tools

7 tools

account_statusAccount statusA

Read-onlyIdempotent

Inspect

Check the signed-in user's Audexum account: plan, credits_left, usage_percent of this period, when credits reset (period_resets), whether engine V4 is available, and a pricing link.

Call it before a long generate_speech or transcribe job to confirm there are enough credits,
when the user asks how much they have left, or after a tool reports insufficient credits.
For what plans include or cost, use audexum_guide; to upgrade, give the user pricing_url.

Read-only and free: it spends no credits and changes nothing. Takes no arguments.

Inputs: no named parameters. Returns: object

audexum_guideAudexum guideA

Read-onlyIdempotent

Inspect

Everything Audexum offers: each engine's strengths, voices, limits and price, every product (dictation app, audiobooks, dubbing, cloning…), plans and credit packs. Call it when the user asks what Audexum can do, which voice or engine to use, or about plans and prices.

Inputs: no named parameters. Returns: object

generate_speechGenerate speechAInspect

Turn text into natural speech and return a link to an MP3 file.

Args:
    text: What to say. Up to 5,000 characters per call (v1: 15,000); split longer text at sentence
        boundaries. On v4 you may put acting tags inline: <laugh> <sigh> <whispers> <short pause> …
    engine: "v4" = most natural (Creator plan and above), "v3" = natural named voices,
        "v2" = 31 languages, "v1" = cheapest. Omit for a good default.
    voice: Voice id from list_voices (e.g. "Kore" on v4, "Atlas" on v3, "F1" on v2). A v4 voice
        name selects v4 by itself.
    language: ISO 639-1 code of the text, e.g. "en", "de", "bg". Default "en".
    style: Optional delivery direction in plain words, e.g. "warm and slow" (v4 and v3).
    speed: 0.5–2.0. Omit for the voice's natural pace.

Spends the user's Audexum credits (characters × the engine's multiplier).

Inputs: text (required), speed, style, voice, +2 more. Returns: object

get_upgrade_linkUpgrade linkA

Read-onlyIdempotent

Inspect

A link where the user can upgrade their Audexum plan or buy credits (which also unlocks V4). Call this when the user asks how to get more credits, V4, or upgrade.

Inputs: no named parameters. Returns: object

list_voicesList voicesA

Read-onlyIdempotent

Inspect

All voices by engine, best first. Pass a voice id (and its engine) to generate_speech.

Inputs: no named parameters. Returns: object

transcribeTranscribe audioAInspect

Transcribe speech in an audio or video file to text.

Args:
    audio_url: Public http(s) URL of the file (mp3, wav, m4a, mp4, webm, ogg…), max 25 MB.
    language: Optional ISO 639-1 hint, e.g. "en". Auto-detected when omitted.

Spends the user's Audexum credits. For YouTube links use youtube_transcript instead.

Inputs: audio_url (required), language. Returns: object

youtube_transcriptYouTube transcriptA

Read-onlyIdempotent

Inspect

Get the transcript (captions) of a YouTube video, via Audexum's API (https://audexum.com/docs).

Args:
    url: A YouTube video link.
    language: Preferred caption language, ISO 639-1. Default "en".

Free — does not spend credits (a daily allowance applies).

Inputs: url (required), language. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Related MCP Connectors

TTSForFreeA
io.github.CalmNguyen
Generate AI voices, text-to-speech, subtitles, transcription, and video localization.
Text-to-Speech Speech Processing Audio Processing
251
https://api.ttsforfree.com/mcp
transcriptionA
com.scriptivox.www
Transcribe audio and video and work with your transcript library from any AI app. 119 languages.
Speech Processing Audio Processing AI & Machine Learning
19
https://platform.scriptivox.com/mcp
VocalLab
ai.vocallab
Text to speech in 200+ languages, voice cloning, voice design and SRT captions.
Text-to-Speech Audio Processing Speech Processing
1
https://mcp.vocallab.ai/mcp
LazybirdA
io.github.lazybirdai
Natural AI voiceovers: search 500+ voices, generate speech, design and save custom voices.
Text-to-Speech Speech Processing AI & Machine Learning
171
https://api.lazybird.app/mcp

Related MCP Servers

tts-mcp-server
Text-to-Speech Speech Processing Audio Processing
RTY2345RR
A
license
Not graded
quality
B
maintenance
Enables AI agents to turn scripts into narration audio with matching SRT/VTT captions in one tool call, plus voice cloning from a reference clip and transcription of local audio or video into subtitles.
Updated 5 days ago (2026-11-08 13:37 UTC)
MIT
transcript-tts
Text-to-Speech Speech Processing Audio Processing
ShevinuM
F
license
A
quality
D
maintenance
Converts text or transcripts into MP3 audio using Microsoft Edge's free neural voices. Provides text-to-speech and voice listing tools with no API key required.
Updated 3 months ago (2026-08-11 06:43 UTC)
2
-
Miragea MCP
Text-to-Speech Speech Processing Audio Processing
yyert123
A
license
Not graded
quality
C
maintenance
Enables AI agents to convert any-length text to speech in saved or cloned voices, generate SRT/VTT captions from local media, and produce per-scene narration with exact durations and frame timings for video timelines.
Updated 4 days ago (2026-11-10 02:23 UTC)
MIT
FreeTTS
Audio Processing Speech Processing Text-to-Speech
freetts
A
license
A
quality
B
maintenance
Text to speech in 149 languages: MP3 links from any assistant. Free without an account. 2,253 voices; PRO adds HD voices, WAV, dialogue with a voice per speaker, Script mode timing and transcription.
Updated 16 days ago (2026-10-28 16:34 UTC)
7
56 npm
MIT